Dictionary Learning-Based Sparse Channel Representation and Estimation for FDD Massive MIMO Systems

Abstract

This paper addresses the problem of uplink (UL) and downlink (DL) channel estimation in frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. By utilizing the sparse recovery and compressive sensing algorithms, we are able to improve the accuracy of the UL/DL channel estimation and reduce the number of UL/DL pilot symbols. Such successful channel estimation builds upon the assumption that the channel can be sparsely represented under some basis/dictionary. Previous works model the channel using some predefined basis/dictionary; while in this paper, we present a dictionary learning-based channel model such that a dictionary is learned from comprehensively collected channel measurements. The learned dictionary adapts specifically to the cell characteristics and promotes a more efficient and robust channel representation, which in turn improves the performance of the channel estimation. Furthermore, we extend the dictionary learning-based channel model into a joint UL/DL learning framework by observing the reciprocity of the angle of arrival/angle of departure between the UL/DL transmissions and propose a joint channel estimation algorithm that combines the UL and DL received training signals to obtain a more accurate channel estimate. In other words, the DL training overhead, which is a bottleneck in FDD massive MIMO system, can be reduced by utilizing the information from simpler UL training.